Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/gmantoha/ctrlx-os-agent-skills/agents-mdgit clone --depth 1 https://github.com/gmantoha/ctrlx-os-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/gmantoha/ctrlx-os-agent-skills/agents-md)<a href="https://agentmods.dev/instructions/gmantoha/ctrlx-os-agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/gmantoha/ctrlx-os-agent-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00567 | $0.00567 |
| Opus 5 | $0.00283 | $0.00283 |
| Sonnet 5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
ctrlx-os-agent-skills AGENTS.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Tools found → use them directly, skip REST/curl How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ctrlX OS Agent Skill Repository
Start Here
- Device involved? → Check MCP first:
tool_search_tool_regex("datalayer|ctrlx")- Tools found → use them directly, skip REST/curl
- Not found → use workflows below
- Pick workflow from
workflows/that matches the task - Read
reference/AGENTS.mdfor platform rules before making assumptions - Use recipe from
recipes/when a concrete playbook exists - Confirm before any persistent change on a real device
Routing
| Task | Workflow |
|---|---|
| Device interaction (MCP available) | workflows/use-mcp.md |
| Crash / OOM / service failure / logs | workflows/debug-issue.md |
| Network / VPN / firewall / users / certs | workflows/configure-device.md |
| App install / update / remove | workflows/manage-apps.md |
| Snap build / Data Layer app / SDK | workflows/build-app.md |
| REST automation / external client | workflows/use-rest-api.md |
| Device Portal templates / serial commissioning | workflows/device-portal-templates.md |
| Data Layer reads / writes / PLC IPC | workflows/use-datalayer.md |
| File transfer / app data | workflows/use-webdav.md |
| UI config / Playwright | workflows/use-web-ui.md |
| Customer / colleague answer | workflows/answer-customer.md |
| ctrlX OS update | workflows/update-os.md |
| Virtual lab | workflows/use-virtual-core.md |
Safety Rules
Safe without confirmation: reading docs, logs, local files, drafting commands/code/answers.
Require confirmation on real device:
- app install / remove / update
- network / firewall / VPN / certificates / users / storage changes
- service restarts, reboots
- any config write via REST, SSH, WebDAV, or Web UI
Folder Intent
workflows/: agent entry points per task typereference/: platform knowledge, best practices, app referencesrecipes/: concrete playbooks for recurring procedureslabs/: virtual ctrlX lab guides and scriptscases/: reusable sanitized investigationscustomers/: private workspaces, excluded from git
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 56 lines · 567 tokens per session scan A 82fd454ba913
ctrlx-os-agent-skills AGENTS.md is an instructions file published in the GitHub repository gmantoha/ctrlx-os-agent-skills (6 stars, last pushed yesterday), licensed MIT. It adds 567 tokens to every session, about $0.0028 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
cml-mcp AGENTS.md
AGENTS.md instructions for xorrkaz/cml-mcp, covering agents.md — cml mcp server, project overview, compatibility goal, repository layout and tool modules (src/cmlmcp/tools/).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
cad-cae-copilot copilot-instructions.md
Copilot instructions for armpro24-blip/cad-cae-copilot, covering github copilot — aieng workspace and essentials.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
zmk-config AGENTS.md
AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.